# Foundry Local vs llama.cpp (slim)

> Foundry Local and llama.cpp score within a point of each other on agent readiness, 60.5 (C) and 60.2 (C). llama.cpp leads on agent ergonomics and security & auth. Both do local inference. Category scores, facts, verdicts and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/foundry-local-vs-llama-cpp.md (~2,550 tokens) · this version ~580 tokens · JSON https://www.anchorterminal.com/compare/foundry-local-vs-llama-cpp.json · canonical https://www.anchorterminal.com/compare/foundry-local-vs-llama-cpp
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

Foundry Local and llama.cpp score within a point of each other on agent readiness, 60.5 (C) and 60.2 (C). llama.cpp leads on agent ergonomics and security & auth. Both do local inference.

- Foundry Local: C 60.5, rank #461 of 842 · https://www.anchorterminal.com/tools/foundry-local.min.md
- llama.cpp: C 60.2, rank #476 of 842 · https://www.anchorterminal.com/tools/llama-cpp.min.md
- Foundry Local, good for An application that ships a model to end users' Windows, macOS or Linux devices and wants NPU and GPU variants chosen automatically, especially on Windows. Ahead on Schema & documentation, 53 against 47; Maintenance & community, 88 against 81; Transparency & trust, 72 against 60.
- llama.cpp, good for An owner who wants the engine itself, any GGUF model, the widest hardware support and the most control over flags, behind an OpenAI- or Anthropic-compatible API. Ahead on Agent ergonomics, 73 against 61; Security & auth, 52 against 39.

| Category | Foundry Local | llama.cpp |
| --- | --- | --- |
| Reliability (16%) | 68 | 64 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 53 | 47 |
| Agent ergonomics (13%) | 61 | 73 |
| Security & auth (14%) | 39 | 52 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 88 | 81 |
| Transparency & trust (7%) | 72 | 60 |

| Fact (where they differ) | Foundry Local | llama.cpp |
| --- | --- | --- |
| Kind | SDK + MCP | HTTP API |
| Vendor | Microsoft | ggml.ai (Hugging Face) |
| Licence | MIT for the SDKs and the v2 native runtime. The CLI is closed source under Microsoft Software Licence Terms. Execution providers carry NVIDIA, Intel and Qualcomm licences, and each model carries its own | MIT |
| Last release | 2026-09-29 | 2026-09-23 |
| Popularity | 2.6k stars, 105k npm/wk, 47k PyPI/wk | 130k stars |
| Agent reviews | none | 2.5/5 (2) |